Best Local LLMs for the Mac Studio M5 Max (48 GB)

The best local LLM for a Mac Studio M5 Max (48 GB) is Qwen 3.6-35B-A3B at 130 tok/s (community run). Its 48 GB fits 71 of the 130 models in the LLMCheck index, up to 80B-class. For everyday chat and coding, Qwen 3.6-35B-A3B is the sweet spot.

Unified memory
48
GB
Mem. bandwidth
614
GB/s
Models that fit
71
of 130
Top speed
estimated285
tok/s

Considering this Mac?
Mac Studio M5 Max (48 GB): build-to-order from Apple · Mac Studio M5 Max (36 GB) on Amazon → · not sure? the Mac Advisor picks a config →

Top 3 picks for the Mac Studio M5 Max (48 GB)

⭐ Best overall
35B MoE · Apache 2.0 · cap 38/50 · agent-ready 64K
community130 tok/s
⚡ Fastest
1.73B · LFM Open · cap 17/50 · agent-ready 64K
estimated285 tok/s
🧠 Most capable
27.8B · Apache 2.0 · cap 46/50 · agent-ready 64K
community31 tok/s

Every model ranked for a Mac Studio M5 Max (48 GB)

Ranked by LLMCheck suitability (capability balanced against speed on the M5 Max); the top pick is the best-ranked model that reaches 15 tok/s here, has a standard Mac runtime and fits the GPU memory limit (raised if need be), and slower models are tagged slow. Click a model for its full figures and setup. Every speed carries its provenance mark: most are index estimates from the memory-bandwidth model, a filled square is a published figure and a hollow circle a community run — submit a real run →

#ModelSizeLicenseSpeed64K contextCapability
1Qwen 3.6-35B-A3B35B MoEApache 2.0community130 tok/sagent-ready38/50
2Recursive Flint39.8B MoEApache 2.0community123 tok/sagent-ready37/50
3North Mini Code 1.030.5B MoEApache 2.0community120 tok/sagent-ready36/50
4Nemotron 3.5 Lightning30B MoEOpenMDWcommunity117 tok/sagent-ready36/50
5LFM2.5-24B-A2B24B MoELFM Opensourced184 tok/sagent-ready35/50
6Qwen3.8-27B27.8BApache 2.0community31 tok/sagent-ready46/50
7KAT-Coder-V2.535B MoEApache 2.0community89 tok/sagent-ready39/50
8Nanbeige4.3-33B33.1BApache 2.0community25 tok/sagent-ready46/50
9Raon-1 mini preview28.8B MoEApache 2.0estimated123 tok/sagent-ready34/50
10GLM-4.7-Flash31B MoEMITestimated107 tok/sagent-ready35/50
11Gemma 4 26B-A4B26B MoEApache 2.0sourced107 tok/sagent-ready35/50
12Qwen 3.6-27B27BApache 2.0estimated30 tok/sagent-ready44/50
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Showing the top 12 of 71 models that fit in 48 GB. See the full leaderboard or all benchmarks.

Estimated figures come from the bandwidth formula; against 163 measured runs its typical error is ±9% for dense models and ±15% for small MoEs (≤40B total). How the error is computed →

Context: “fits” means the weights at a short prompt. Coding agents (Claude Code, OpenCode, Codex CLI) hold 64K tokens or more, and every token adds KV cache: agent-ready marks a model whose weights plus a 64K-token 16-bit KV cache still fit in the 42 GB this Mac’s GPU can use with the limit raised (57 of the 66 models here with a KV figure). That is an estimate from each model’s config.json, not a measurement; a q8 KV cache halves the cache part, and — means the index has no KV figure for the model yet. The GPU memory limit below applies on top.

GPU memory limit: macOS lets the GPU use about 37.4 GB of this Mac’s 48 GB by default (macOS 26 and later, the only macOS it runs). Of the 71 models that fit, 7 need more than that at a short prompt: 3 need a raised limit and are tagged raise GPU limit (Nemotron 3.5 Bolt 74B-A9B and Llama 3.3 70B only past the safe setting below, as measured runs on this much memory show); 4 need more than even the raised limit and are tagged over GPU limit. sudo sysctl iogpu.wired_limit_mb=43008 raises it to 42 GB, leaving 6 GB for macOS, until the Mac restarts (sudo sysctl iogpu.wired_limit_mb=0 restores the default). How the limit is read →

Quick start: run Qwen 3.6-35B-A3B on your Mac Studio M5 Max

The fastest way to get started is Ollama. Install it, then pull the model by its tag (checked on ollama.com, 2026-11-14):

brew install ollama

ollama run qwen3.6:35b-a3b · model card →

Prefer a GUI? LM Studio gives you a one-click download and chat window. For step-by-step help see our Ollama install guide, or open the Qwen 3.6-35B-A3B on M5 Max page for its figures and setup.

Same Mac with more memory, and the upgrade path

Upgrade or save: Qwen 3.6-35B-A3B on other Macs

Same pick, other Macs

Twice as fast: no Mac in the index runs Qwen 3.6-35B-A3B at twice this Mac’s community130 tok/s; the fastest figure is the Mac Studio M5 Ultra (96 GB) at community153 tok/s, $5,499 new (Apple list price, checked 2026-11-14): build-to-order from Apple (Amazon does not stock this configuration).

For less: the cheapest Mac that still runs Qwen 3.6-35B-A3B at 15+ tok/s is the MacBook Air M2 (24 GB) at estimated~43 tok/s, about $850 refurbished or used: search Amazon Renewed listings →. New: the Mac mini M6 (24 GB) at community59 tok/s, $1,099 new (Apple list price, checked 2026-11-14): Mac mini M6 (24GB) on Amazon →.

Speeds are each Mac’s own figure from the index, with its provenance mark. Prices come from data/macs.json: Apple’s list price for a new Mac (dated), an approximate street price for a used or refurbished one. Amazon stock checked 2026-11-18. Amazon links are affiliate links: as an Amazon Associate, LLMCheck earns from qualifying purchases.

🛒 Get a Mac Studio M5 Max for local AI

The Mac Studio M5 Max (48 GB) runs 71 of the models in the LLMCheck index, led by Qwen 3.6-35B-A3B. This 48 GB configuration is build-to-order from Apple: Amazon does not stock it (it carries the standard 36 GB Mac Studio M5 Max, with less memory).

As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence our rankings.

Cite this page

LLMCheck. (2026). Best Local LLMs for the Mac Studio M5 Max (48 GB). llmcheck.net. https://llmcheck.net/best-llm/mac-studio-m5-max-48gb/ (updated ). CC BY 4.0.

How to cite LLMCheck →Data: CC BY 4.0Markdown version

FAQ: local LLMs on the Mac Studio M5 Max

What is the best local LLM for a Mac Studio M5 Max (48 GB)?

Qwen 3.6-35B-A3B (35B MoE, Apache 2.0) is the best all-round pick at 130 tok/s (community run) on the Mac Studio M5 Max. If you want maximum speed, LFM3-1.7B hits ~285 tok/s (estimated); for maximum capability, Qwen3.8-27B still fits in 48 GB.

How many models can a Mac Studio M5 Max with 48 GB run?

About 71 of the 130 models in the LLMCheck index fit in 48 GB of unified memory, from compact models up to Qwen3-Coder-Next (80B MoE).

Can a Mac Studio M5 Max run a 70B model?

Just. A dense 70B such as Llama 3.3 70B needs about 44 GB at 4-bit, which leaves little of the 48 GB for context and other apps; the index puts it at 13 tok/s (published figure) here.

Is 48 GB of RAM enough to run LLMs locally?

48 GB is enough for dense models up to about 72B at 4-bit (the largest in the index that fits is Qwen 2.5 72B), and for mixture-of-experts models such as Nemotron 3.5 Bolt 74B-A9B (~55 tok/s (estimated)). As a rule of thumb a 4-bit model needs about 0.57 GB per billion parameters plus ~2 GB, and macOS needs its own share of memory too. Because Apple Silicon uses unified memory, the same pool serves as system RAM and GPU memory.

Related